Sitemap - 2024 - LLM Watch

๐ŸŽ Meta Reveals New AI Architecture

๐ŸŒฑ Another ChatGPT Moment

๐Ÿ—ฃ๏ธ Microsoft's Best Small Language Model

๐ŸงชThe First Fully AI-Designed Drug... Almost

๐Ÿฅ‡ GraphRAG's Biggest Problem Solved

A Non-Technical Introduction to AI Agents

๐Ÿ“ Actually Open AI: A Free o1 Alternative

๐Ÿค– The Future of Designing AI Agents

๐Ÿ’ป HTML > Plain Text for RAG

๐Ÿค All You Need to Know About Small Language Models

Stream of Search: Teaching Language Models the Language of Search

๐Ÿง  Is AI Capable of Reflection?

AI for Science: How to turn your LLM into an Innovation Machine

๐Ÿ—ƒ๏ธ GraphRAG Evolves into StructRAG

StructRAG: Succeeding Where Graph RAG Fails

๐Ÿ”‹ Fixing AI's Energy Consumption

๐Ÿ“ Chasing o1: Closing the Reasoning Gap

โ™ป๏ธ LLMs Are Improving Themselves

SFR-RAG: How Open AI Can Beat OpenAI

๐Ÿ“ A New Neural Architecture (Again)

Google's RAG Alternative: Retrieval Interleaved Generation (RIG)

๐Ÿš€ What Next-Gen RAG Is About

How AI Is Generating Novel Research Ideas

๐Ÿง  The Next Level of CoT Prompting

๐Ÿ“Š Agents for Time Series Analysis

Your Introduction to Microsoft GraphRAG

Automated Design of Agentic Systems (ADAS)

๐Ÿ‘๏ธ Agent-ception: When Agents Are Creating Agents

๐ŸŽ Apple's Answer to Complex LLM Evaluation

๐Ÿ˜ฎ The Downsides of Structured Outputs

๐Ÿ‘๏ธโ€๐Ÿ—จ๏ธ Attention Is All Graphs Need

๐Ÿ“š A Historic Week for ฬถOฬถpฬถeฬถnฬถ ฬถSฬถoฬถuฬถrฬถcฬถeฬถ AI

โŒ When Accuracy Isn't Enough - Don't Make This Mistake

๐Ÿ›’ Getting RAG Right: All in One Go

โ“ Are You Doing RAG Right?

๐Ÿ’ช Is Google Back in the AI Race?

๐Ÿค” Has OpenAI Lost Its Edge?

โซ From Memorization to Generalization

โ™ป๏ธ Improving RAG with Self-Feedback

๐Ÿ•ต๏ธ The Dawn of Foundation Agents

๐Ÿค– ChatGPT failing 92% of the time

๐Ÿ—ฃ๏ธ - OpenAI Reaching for Omnipotence

๐Ÿ’ฃ The LSTMpire Strikes Back

๐Ÿ“š A New Direction for Neural Networks

๐Ÿ Apple Unveals Their Secrets

โ™พ๏ธ Scaling LLMs 2 Infinity

๐Ÿค” LLMs Struggle With Causality

๐Ÿ‘๏ธโ€๐Ÿ—จ๏ธ LLMs Opening Their Inner Eyes

๐Ÿ‘‹ A New AI Software Engineer

๐Ÿ”ฎ Moving beyond RAG

๐ŸŽ - BIG News from Apple

โš™๏ธ 3 Ways to Efficient AI

๐Ÿ’ฅ Breaking Compute Barriers

๐Ÿ“ข The Next Phase of Scaling LLMs

โญ The In-Context Revolution

๐Ÿ”ด Gotta Catch 'Em All!

๐Ÿฅฑ The End of Lazy LLMs

โŒ› Time for LLMs?

๐Ÿค” Cogito ergo sum()

๐Ÿง‘โ€๐Ÿ”ฌ The Next Impact Factor

๐Ÿ“ We Need New Benchmarks